Prótese Mioelétrica 3D Inteligente Utilizando Redes Neurais Artificiais e Internet das Coisas para Auxílio a Reabilitação de Soldados em Ambientes Remotos

[...]assistance may be limited, since access to the patient is reduced, especially in remote environments such as war. [...]the main objective of this article is to present the development of an intelligent myolmetric prosthesis, made using low cost 3D printing technology and techniques of processing and classification by artificial neural networks, as well as, remote communication using the Internet of Things, in order to allow the monitoring and control of prostheses remotely, aiding in the rehabilitation of soldiers, at a distance, as in war environments. Entre as funçoes estatísticas para esse tipo de pré-processamento, foram utilizadas as seguintes: * Mean absolut value - MAV; * Waveform length - WL; * Root mean square - RMS; * Difference Absolute Standard Deviation Value - DASDV; * Log Detector - LOG; * V-Order - V; Assim, ao se fazer o pré-processamento, é possível ter 14 características de entrada para classificaçao. Referencias Nayak, S. et al., "Development of a simultaneous acquisition system for ECG, PCG and body temperature signals," in 2015 Annual IEEE India Conference (INDICON), 2015, pp. 1-6. Enabling IoT for In-Home Rehabilitation: Accelerometer Signals Classification Methods for Activity and Movement Recognition.